fix: resolve all ruff linting errors and add lint CI check

- Fix ambiguous fullwidth characters (commas, parentheses) in strings and comments
- Replace Chinese comments with English equivalents
- Fix unused imports with proper noqa annotations for intentional imports
- Fix bare except clauses with specific exception types
- Fix redefined variables and undefined names
- Add ruff noqa annotations for generated protobuf files
- Add lint and format check to GitHub Actions CI pipeline

test/sanity_checks/benchmark_embeddings.py

@@ -1,43 +1,46 @@
 import time
-import numpy as np
+
 import matplotlib.pyplot as plt
-import torch
-from sentence_transformers import SentenceTransformer
 import mlx.core as mx
+import numpy as np
+import torch
 from mlx_lm import load
+from sentence_transformers import SentenceTransformer
 
 # --- Configuration ---
 MODEL_NAME_TORCH = "Qwen/Qwen3-Embedding-0.6B"
 MODEL_NAME_MLX = "mlx-community/Qwen3-Embedding-0.6B-4bit-DWQ"
 BATCH_SIZES = [1, 8, 16, 32, 64, 128]
 NUM_RUNS = 10  # Number of runs to average for each batch size
-WARMUP_RUNS = 2 # Number of warm-up runs
+WARMUP_RUNS = 2  # Number of warm-up runs
 
 # --- Generate Dummy Data ---
 DUMMY_SENTENCES = ["This is a test sentence for benchmarking." * 5] * max(BATCH_SIZES)
 
 # --- Benchmark Functions ---b
 
+
 def benchmark_torch(model, sentences):
     start_time = time.time()
     model.encode(sentences, convert_to_numpy=True)
     end_time = time.time()
     return (end_time - start_time) * 1000  # Return time in ms
 
+
 def benchmark_mlx(model, tokenizer, sentences):
     start_time = time.time()
-    
+
     # Tokenize sentences using MLX tokenizer
     tokens = []
     for sentence in sentences:
         token_ids = tokenizer.encode(sentence)
         tokens.append(token_ids)
-    
+
     # Pad sequences to the same length
     max_len = max(len(t) for t in tokens)
     input_ids = []
     attention_mask = []
-    
+
     for token_seq in tokens:
         # Pad sequence
         padded = token_seq + [tokenizer.eos_token_id] * (max_len - len(token_seq))
@@ -45,24 +48,25 @@ def benchmark_mlx(model, tokenizer, sentences):
         # Create attention mask (1 for real tokens, 0 for padding)
         mask = [1] * len(token_seq) + [0] * (max_len - len(token_seq))
         attention_mask.append(mask)
-    
+
     # Convert to MLX arrays
     input_ids = mx.array(input_ids)
     attention_mask = mx.array(attention_mask)
-    
+
     # Get embeddings
     embeddings = model(input_ids)
-    
+
     # Mean pooling
     mask = mx.expand_dims(attention_mask, -1)
     sum_embeddings = (embeddings * mask).sum(axis=1)
     sum_mask = mask.sum(axis=1)
     _ = sum_embeddings / sum_mask
-    
+
     mx.eval()  # Ensure computation is finished
     end_time = time.time()
     return (end_time - start_time) * 1000  # Return time in ms
 
+
 # --- Main Execution ---
 def main():
     print("--- Initializing Models ---")
@@ -92,13 +96,15 @@ def main():
     for batch_size in BATCH_SIZES:
         print(f"Benchmarking batch size: {batch_size}")
         sentences_batch = DUMMY_SENTENCES[:batch_size]
-        
+
         # Benchmark PyTorch
         torch_times = [benchmark_torch(model_torch, sentences_batch) for _ in range(NUM_RUNS)]
         results_torch.append(np.mean(torch_times))
-        
+
         # Benchmark MLX
-        mlx_times = [benchmark_mlx(model_mlx, tokenizer_mlx, sentences_batch) for _ in range(NUM_RUNS)]
+        mlx_times = [
+            benchmark_mlx(model_mlx, tokenizer_mlx, sentences_batch) for _ in range(NUM_RUNS)
+        ]
         results_mlx.append(np.mean(mlx_times))
 
     print("\n--- Benchmark Results (Average time per batch in ms) ---")
@@ -109,20 +115,21 @@ def main():
     # --- Plotting ---
     print("\n--- Generating Plot ---")
     plt.figure(figsize=(10, 6))
-    plt.plot(BATCH_SIZES, results_torch, marker='o', linestyle='-', label=f'PyTorch ({device})')
-    plt.plot(BATCH_SIZES, results_mlx, marker='s', linestyle='-', label='MLX')
+    plt.plot(BATCH_SIZES, results_torch, marker="o", linestyle="-", label=f"PyTorch ({device})")
+    plt.plot(BATCH_SIZES, results_mlx, marker="s", linestyle="-", label="MLX")
 
-    plt.title(f'Embedding Performance: MLX vs PyTorch\nModel: {MODEL_NAME_TORCH}')
+    plt.title(f"Embedding Performance: MLX vs PyTorch\nModel: {MODEL_NAME_TORCH}")
     plt.xlabel("Batch Size")
     plt.ylabel("Average Time per Batch (ms)")
     plt.xticks(BATCH_SIZES)
     plt.grid(True)
     plt.legend()
-    
+
     # Save the plot
     output_filename = "embedding_benchmark.png"
     plt.savefig(output_filename)
     print(f"Plot saved to {output_filename}")
 
+
 if __name__ == "__main__":
     main()